Postdoctoral Appointee - Machine Learning, Control, and Cybersecurity for Power Systems

The Energy Systems and Infrastructure Assessment Division at Argonne National Laboratory is seeking a highly motivated Postdoctoral Appointee to support research on AI-enabled monitoring, control, and cyber-resilient operation of distribution systems and networked microgrids. The successful candidate will contribute primarily to the control and cybersecurity thrusts of a multi-institutional project focused on AI-enabled resilient operation of distribution systems and networked microgrids under uncertainty, disturbances, and cyber-physical threats.

This position is best suited for a candidate with strong expertise in machine learning for cyber-physical systems and a solid understanding of electric power distribution systems, and microgrid operations. The selected candidate will develop and evaluate advanced algorithms for applications such as secure and adaptive control, anomaly and attack detection, resilient decision-making, and AI-enabled operational support for highly distributed grids. The postdoctoral appointee will work closely with multidisciplinary teams at Argonne and partner institutions and is expected to contribute to both methodological innovation and practical validation using simulation, co-simulation, or hardware-relevant environments.

Primary Responsibilities:

• Develop machine learning and AI methods for control, optimization, and cyber-resilient operation of distribution systems, DER, and networked microgrids.
• Design and implement reinforcement learning, game-theoretic, or robust decision-making approaches for adaptive control of DER and microgrids under uncertainty and adversarial conditions.
• Develop methods for cyberattack detection, anomaly identification, intrusion-aware control, and resilient system recovery in cyber-physical energy systems, including DER-rich distribution networks.
• Integrate domain knowledge from power systems with modern ML methods to create physics-informed, interpretable, and operationally relevant solutions.
• Build and evaluate models using realistic utility or test-system data, simulation platforms, and digital-twin or real-time environments as appropriate.
• Collaborate with researchers across power systems, controls, cybersecurity, and AI/ML to develop publications, technical reports, software tools, and project deliverables.
• Present research results at technical meetings, workshops, and leading conferences, and publish in high-impact journals.

• Recent or soon-to-be completed (typically within the last 0-5 years ) Ph.D. in Computer Science, Electrical Engineering, or a related field.
• Demonstrated research expertise in AI and machine learning, with application to power systems, control, optimization, or cybersecurity.
• Programming skills in Python and experience with at least one modern machine learning framework such as PyTorch or TensorFlow.
• Demonstrated experience in at least one of the following: reinforcement learning, control or optimization for cyber-physical systems, anomaly detection, cybersecurity for operational systems, or decision-making under uncertainty.
• Working knowledge of electric power systems, with emphasis on distribution systems, microgrids, or inverter-based resources.
• Evidence of scholarly research productivity, such as peer-reviewed journal papers, conference publications, technical reports, or an equivalent research record.
• Skilledritten and verbal communication skills and the ability to work effectively in a multidisciplinary research environment.
• Ability to model Argonne’s core values of impact, safety, respect, integrity, and teamwork.
• This position requires an on-site presence at the Argonne campus in Lemont, Illinois., * Direct research experience at the intersection of machine learning and power system operation, especially for distribution systems, and microgrids.
• Experience with power system simulation or analysis tools such as OpenDSS or similar platforms.
• Experience with real-time simulation, co-simulation, digital twins, hardware-in-the-loop, or testbed-based validation.
• Experience working with utility, field, or experimentally derived datasets relevant to grid operations, control, or cybersecurity.
• Experience contributing to collaborative research software, reproducible workflows, or open-source tool development.